Create multimodal embeddings

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds value beyond sparse annotations by noting that image input may require feature enablement, alerting the agent to potential access restrictions. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, mostly concise, but the first sentence redundantly restates the title. Could be trimmed without loss.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Missing details on output format (embedding vector), input structure (object vs array), behavior when both text and image are provided, and error handling. No output schema to compensate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description largely repeats the schema's own description for the 'input' parameter and does not add new meaning for 'model' or 'dimensions'. With 67% schema coverage, the description offers negligible additional value for parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Create' and the resource 'multimodal embeddings', and distinguishes from siblings like 'create_embedding' by specifying multimodal input. It also provides context on text vs image availability.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use the tool (when multimodal embeddings are needed) but does not explicitly state when not to use it or mention alternatives like 'create_embedding' for text-only use cases.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.